Disclosed is a face verification method and apparatus. The method including analyzing a current frame of a verification image, determining a current frame state score of the verification image indicating whether the current frame is in a state predetermined as being appropriate for verification, determining whether the current frame state score satisfies a predetermined validity condition, and selectively, based on a result of the determining of whether the current frame state score satisfies the predetermined validity condition, extracting a feature from the current frame and performing verification by comparing a determined similarity between the extracted feature and a registered feature to a set verification threshold.

Systems that search databases of videos or images to identify similar products in a given video or image of a product are disclosed. The content of the given video is represented by a feature vector used to measure the given video's similarity to either a video or an image. When the system is deployed to recognize particular fashion items in videos, some such videos are taken in uncontrolled settings, and as a result, may have low resolution, poor contrast, minimal focus, motion blur, or low lighting. By recognizing and removing poor quality video frames from the image recognition pipeline, associating products across video frames to form tracklets of each product, and enriching the feature representation of each item for best retrieval result by fusing information from multiple video frames depicting the item, the system addresses the aforementioned shortcomings.

An information processing apparatus includes a comparison unit configured to compare an image capturing condition for a collation target object with an image capturing condition for each of a plurality of image capturing apparatuses, a selection unit configured to select an image capturing apparatus to be collated from among the plurality of image capturing apparatuses based on a result of the comparison by the comparison unit, and a collation unit configured to collate information about an object captured by the image capturing apparatus to be collated with information about the collation target object.

An image processing method includes analyzing multiple images data based on Illumination-invariant Feature Network (IF-NET) with an image processing device to generate corresponding sets of eigenvector, in which image data includes a first image data related to at least one first feature of the sets of eigenvector, and a second image data related to at least one second feature of the sets of eigenvector; choosing a corresponding first training set of tiles and second training set of tiles from the first image data and second image data with an image processing device based on IF-NET, and computing on both training set of tiles to generate a least one loss value; and adjusting IF-NET based on a least one loss value. An image processing system is also disclosed herein.

Provided are an image rectification method and apparatus, and an electronic system. The image rectification method includes: acquiring a first image and a second image of the same shooting object by means of a first shooting apparatus and a second shooting apparatus which are coaxially disposed; and correcting the second image according to shooting parameters of the first shooting apparatus and the second shooting apparatus to obtain a second rectified image, such that the parallax between the second rectified image and the first image in a vertical direction or a horizontal direction is zero. In the method, by taking a first image as a reference, and by means of adjusting the shooting parameters of the first shooting apparatus and a second shooting apparatus, only the second image is rectified, thereby improving the operation efficiency of image rectification, and improving the accuracy and stability of an image rectification result.

The application provides a monitoring method, electronic device and storage medium. The method includes determining a target area to be monitored from an acquired image of a monitored scene; determining a target capture posture and a target capture focal length according to the target area; and controlling a Pan Tilt Zoom (PTZ) camera to capture according to the target capture posture and the target capture focal length. The application can monitor any object within the monitored scene using the PTZ camera with a good capture effect.

The present disclosure provides a distance determination method, apparatus and system, relating to the technical field of image processing. The method includes the following steps: acquiring a master visual image photographed by a master camera and an original auxiliary visual image photographed by an auxiliary camera; acquiring an initial matching point pair between the master visual image and the original auxiliary visual image through feature extraction and feature matching; correcting the original auxiliary visual image sequentially, based on the initial matching point pair and different constraints, so as to obtain a target auxiliary visual image, wherein the different constraints includes: a constraint of a minimum rotation angle and a constraint of a minimum parallax; and determining a focusing distance according to the master visual image and the target auxiliary visual image. The focusing distance can be determined more accurately.

A method for training an image segmentation model includes: acquiring target category feature information that represents category features of a training sample and a prediction sample, and associated scene feature information thereof; performing splicing processing on the target category feature information and the associated scene feature information; inputting first spliced feature information obtained by the splicing processing into an initial generation network to perform image synthesis processing; inputting a first synthesized image obtained by the synthesis processing into an initial determination network to determine authenticity; inputting the first synthesized image into a classification network of an initial image segmentation model to perform image segmentation, to obtain a first image segmentation result; and training the classification network of the initial image segmentation model based on a first image determination result, the first image segmentation result, and the target category feature information, so as to obtain a target image segmentation model.

An image capturing apparatus acquires successive images in a time-series manner and performs image processing thereon. The image capturing apparatus detects a first region (for example, a face) of a subject from an image, and detects a second region (for example, a torso) of a subject from an image. The image capturing apparatus performs processing for searching for a detection result which is obtained from a current image with use of a detection result obtained from a previously acquired image and classifying detection results each satisfying a condition according to subject. In the search processing, identical-region search, which uses detection results of an identical region between the previously acquired image and the current image, is performed in preference to different-region search, which uses detection results of different regions between the previously acquired image and the current image.

Embodiments of the present disclosure relate to a method, an electronic device, and a computer program product for data augmentation. The method includes: generating a group of candidate images based on a target image by using a thermodynamic genetic algorithm (TDGA) model, the TDGA model being configured to apply one or more operations of a set of predetermined image processing operations during each evolution process; and determining multiple augmented images from the group of candidate images based on free energy of the group of candidate images, the multiple augmented images being determined as belonging to the same classification with the target image. In this way, data augmentation can be efficiently implemented by a thermodynamic genetic algorithm.